AiCostCompare

Compare models

Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.

Claude Haiku 4.5Step 3.5 Flash
Claude Haiku 4.5

Anthropic

Step 3.5 Flash

Stepfun

Pricing
Input $/1M$1.00$0.10
Output $/1M$5.00$0.30
Blended $/1M (3:1)$2.00$0.15
Cache read $/1M$0.10
Cache write $/1M$1.25
Quality indices
Intelligence Index29.626
Coding Index43.9
Math Index
Agentic Index16.4
Speed & latency
Output speed (tok/s)298
Time to first token0.74s
Time to first answer token7.45s
Benchmarks (Artificial Analysis)
GPQA Diamond82.6%
Humanity's Last Exam22.6%
SciCode38.5%
IFBench66.5%
AA-LCR (Long Context Reasoning)54.3%
Terminal-Bench Hard32.6%
τ²-Bench (Telecom)87.4%
Design Arena (Elo)
Website1,149
UI components1,142
Data viz1,160
SVG1,072
3D1,131
Game dev1,155
Code categories1,148
ASCII art1,182
Specs
Context window200K262K
Max output tokens64K66K
Input modalitiestext, image, filetext
TokenizerClaudeOther